Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terminologies related to programming and coding structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with various symbols and punctuation

    np_acts-logits-general · gemini-2.0-flash

    code structure and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incentiv
    -0.64
    ️
    -0.58
    Lorem
    -0.58
     insights
    -0.56
     ]];
    -0.56
     impactful
    -0.56
     trải
    -0.56
     YouTuber
    -0.55
     🤦
    -0.55
     timeline
    -0.55
    POSITIVE LOGITS
     daß
    1.08
     muß
    1.03
     Daß
    0.97
     idéia
    0.85
     läßt
    0.85
     mußte
    0.84
    faßt
    0.83
     müßte
    0.81
     wußte
    0.78
     Einfluß
    0.72
    Act Density 1.342%

    No Known Activations